In recent years, algorithms and neural architectures based on the Weisfeiler-Leman
algorithm, a well-known heuristic for the graph isomorphism problem, have emerged as a …

We demonstrate MedHunter, a system for assisting the early stage of drug development.
MedHunter builds a biomedical knowledge graph DDKG by integrating data from eleven …

Recent advancements in graph learning have revolutionized the way to understand and
analyze data with complex structures. Notably, Graph Neural Networks (GNNs), ie neural …

Graph isomorphism, a classical algorithmic problem, determines whether two input graphs
are structurally identical or not. Interestingly, it is one of the few problems that is not yet …

Link prediction is a fundamental problem in graph data. In its most realistic setting, the
problem consists of predicting missing or future links between random pairs of nodes from …

Graph Neural Networks (GNNs) have paved its way for being a cornerstone in graph related
learning tasks. From a theoretical perspective, the expressive power of GNNs is primarily …

A hypergraph consists of a set of nodes along with a collection of subsets of the nodes
called hyperedges. Higher-order link prediction is the task of predicting the existence of a …

Abstract This paper reports Fishing Fort, a graph analytic system developed in response to
the following questions. What practical value can we get out of graph analytics? How can we …

The twenty-first century is a data-driven era where human activities and behavior, physical
phenomena, scientific discoveries, technology advancements, and almost everything that …

This thesis contributes to the theoretical understanding of deep learning at two fronts. The
first half of the thesis concerns the training dynamics of wide neural networks (NNs). The …